How much VRAM does LFM2-2.6B-Transcript need?

Q4_K_M is exactly 1,563,669,248 bytes (1.46 GiB) in weights. Add the KV cache, which depends on context length, plus roughly half a gigabyte of runtime overhead.

How large is LFM2-2.6B-Transcript's KV cache?

0.50 GiB at 32K context with an f16 cache, computed per layer from the model's architecture. Quantizing the cache to q8_0 roughly halves it.

LiquidAI · text

LFM2-2.6B-Transcript

LiquidAI/LFM2-2.6B-Transcript

LFM2-2.6B-Transcript at Q4_K_M is exactly 1,563,669,248 bytes (1.46 GiB / 1.56 GB) — an effective 4.869 bits per weight, not the nominal 4. Its KV cache at 32K is 0.50 GiB.

From the file· summed from 1 file(s)From the file· KV per layer

Parameters

2.6B

Architecture

lfm2

30 layers

Context

128,000

native (config.json)

License

—

Shipped quantizations

● exact bytes, summed from published files

Quant	Size●	Exact bytes●	Effective bpw●	Tensors●	Publisher
Q2_K	0.92 GiB	983,806,720	3.063	—	DevQuasar
Q3_K_S	1.08 GiB	1,159,738,112	3.611	—	DevQuasar
Q3_K_M	1.17 GiB	1,256,059,648	3.911	—	DevQuasar
Q3_K_L	1.25 GiB	1,340,863,232	4.175	—	DevQuasar
Q4_K_S	1.39 GiB	1,491,890,944	4.645	—	DevQuasar
Q4_K_M	1.46 GiB	1,563,669,248	4.869	—	DevQuasar
Q5_K_S	1.66 GiB	1,787,458,304	5.566	—	DevQuasar
Q5_K_M	1.70 GiB	1,828,958,976	5.695	—	DevQuasar
Q6_K	1.97 GiB	2,110,829,312	6.572	—	DevQuasar
Q8_0	2.55 GiB	2,733,011,712	8.510	—	DevQuasar
F16	4.79 GiB	5,141,459,712	16.009	—	DevQuasar

KV cache by context

computed per layer

Context	KV cache (f16)●	Flat formula	Overstated by	Full / windowed / recurrent
4,096	0.06 GiB	0.23 GiB	3.75×	8 / 0 / 22
8,192	0.13 GiB	0.47 GiB	3.75×	8 / 0 / 22
16,384	0.25 GiB	0.94 GiB	3.75×	8 / 0 / 22
32,768	0.50 GiB	1.88 GiB	3.75×	8 / 0 / 22
65,536	1.00 GiB	3.75 GiB	3.75×	8 / 0 / 22
131,072	2.00 GiB	7.50 GiB	3.75×	8 / 0 / 22

22 of 30 layers use linear attention, which keeps a fixed-size recurrent state instead of a per-token cache. Those layers do not grow with context at all — treating them as ordinary attention, as a flat formula does, overstates this model's cache by roughly 3.8× at long context.

Compare with

same modality, comparable size

vs Qwen3-4B vs Qwen3-8B vs HyperCLOVAX-SEED-Text-Instruct-1.5B vs Llama-3.2-1B-Instruct vs Qwen3-VL-8B-Instruct-abliterated-v1 vs Llama-3.1-8B-Instruct All alternatives →Will it fit on my card? →

Why other calculators give a different number

A parameters × bits ÷ 8 estimate puts Q4_K_M at roughly 1.35 GiB. The real file is 1.46 GiB, because a quantization is a mixture and some tensors are always kept at higher precision.

Architecture

from config.json

Layers

Attention heads

KV heads

Head dim

Hidden size

2048

Vocab

65,536

Sliding window

none

SWA period

—

MLA

Experts

—

Experts per token

—

use_sliding_window

—

Questions people ask

How much VRAM does LFM2-2.6B-Transcript need?: Q4_K_M is exactly 1,563,669,248 bytes (1.46 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
How large is LFM2-2.6B-Transcript's KV cache?: 0.50 GiB at 32K context with an f16 cache, computed per layer. Quantizing the cache to q8_0 roughly halves it, which is often the difference between a context length fitting and not.
Which quantization of LFM2-2.6B-Transcript should I use?: Q4_K_M is the usual default. Pick the largest quantization that fits your card at the context you actually need — the table above gives exact sizes for every one published.